Precise Detection in Densely Packed Scenes
This addresses the challenge of detecting numerous, often identical objects in close proximity, which is critical for applications like inventory management in retail, but it appears incremental as it builds on existing deep-learning detection frameworks.
The paper tackles the problem of precise object detection in densely packed scenes, such as retail environments, and shows that their method outperforms existing state-of-the-art approaches with substantial margins on datasets like SKU-110K, CARPK, and PUCPR+.
Man-made scenes can be densely packed, containing numerous objects, often identical, positioned in close proximity. We show that precise object detection in such scenes remains a challenging frontier even for state-of-the-art object detectors. We propose a novel, deep-learning based method for precise object detection, designed for such challenging settings. Our contributions include: (1) A layer for estimating the Jaccard index as a detection quality score; (2) a novel EM merging unit, which uses our quality scores to resolve detection overlap ambiguities; finally, (3) an extensive, annotated data set, SKU-110K, representing packed retail environments, released for training and testing under such extreme settings. Detection tests on SKU-110K and counting tests on the CARPK and PUCPR+ show our method to outperform existing state-of-the-art with substantial margins. The code and data will be made available on \url{www.github.com/eg4000/SKU110K_CVPR19}.